Everything for Codex

Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,341 indexed, measured the same four ways as everything else here.

find-skills

13609

agentspace-so/skills

Skill Claude CodeCodex

Discover, vet, and install agent skills by searching ACROSS every major registry at once — skills.sh, clawhub.ai, and GitHub — presenting each board on its own native metric (installs / stars) with the top entry per board, security-scanning the top candidates' real SKILL.md for risky patterns, and flagging what's…

not rated 11 5mo ago A Socket: passSnyk: warn 172 tokens original MIT

mcp-image-optimizer

13610

piephai/mcp-image-optimizer

MCP server Claude CodeCodexCursor +2

MCP server for image optimization with URL support. Runs locally from the mcp-image-optimizer npm package.

not rated 11 11mo ago A tokens not measured original MIT

grok-mcp

13611

howardpen9/grok-mcp

MCP server Claude CodeCodexCursor +2

Use xAI Grok as a peer reviewer + PR gate from Claude Code, Cursor, Cline and any MCP host. Runs locally from the grok-cli-mcp npm package.

not rated 11 3mo ago A tokens not measured original MIT

agentspore

13612

AgentSpore/agentspore

MCP server Claude CodeCodexCursor +2

Real-time Python SDK for AgentSpore agents — WebSocket-based event handling with webhook fallback and MCP server. Runs locally from the agentspore-sdk Python package. Needs 2 environment variables to run.

not rated 11 yesterday A tokens not measured

vulnicheck

13613

andrasfe/vulnicheck

MCP server Claude CodeCodexCursor +2

MCP server "vulnicheck" as configured in andrasfe/vulnicheck. Runs in Docker (docker.io/andrasfe/vulnicheck:main). Needs 7 environment variables to run.

not rated 11 8mo ago A tokens not measured original MIT

serkan-ozal/driflyte-mcp-server

MCP server Claude CodeCodexCursor +2

One of 2 in server.json

Discover available topics and explore up-to-date, topic-tagged web content. Search to surface the… Remote server at server.smithery.ai.

not rated 11 1y ago A tokens not measured original MIT

pudge-ui

13615

pudge-studio/pudge-ui

MCP server Claude CodeCodexCursor +2

Query pudge-ui — 93 skeuomorphic 2000s-era UI component specs — for coding-agent context. Runs locally from the @pudge-ui/mcp-server npm package.

not rated 11 1mo ago A tokens not measured original MIT

sshmcp

13616

NikolaNddTesla/ssh-mcp-server

MCP server Claude CodeCodexCursor +2

SSH server management with zero-token SFTP file transfer and SOCKS proxy support. Runs locally from the @nl4ever/sshmcp npm package.

not rated 11 4d ago A tokens not measured

skill-matcher

13617

alexgrebeshok-coder/skill-matcher

Skill Claude CodeCodex

A skill-selection assistant that analyses a request and recommends relevant coding-agent skills from installed or external catalogues.

not rated 11 8mo ago A 0 tokens original MIT

nreki-optimizer

13618

Ruso-0/Nreki

Skill Claude CodeCodex

Edit code through NREKI MCP tools (edits checked for syntax and types before writing) and read only the symbols a task needs.

not rated 11 changed 2d ago A 34 tokens original Apache-2.0

talk-to-figma-design

13619

richardplg2/figma-annotations

Skill Claude CodeCodex

Parse Figma design prompt, enrich via MCP, explore codebase, generate design spec, and invoke brainstorming.

not rated 11 7mo ago A 28 tokens original MIT

mcp

13620

SpaceFrontiers/mcp

MCP server Claude CodeCodexCursor +2

Machine Library: cited search over papers, books, patents and social posts, with agent comments. Remote server at mcp.machinelibrary.ai.

not rated 11 changed 1mo ago A tokens not measured original MIT

kanban

13621

tronschell/kanban-thing

MCP server Claude CodeCodexCursor +2

Create and drive KanbanThing kanban boards. No account, no API key, board link required. Remote server at www.kanbanthing.com.

not rated 11 3mo ago A tokens not measured original MIT

Crawleo-MCP

13622

Crawleo/Crawleo-MCP

MCP server Claude CodeCodexCursor +2

Hosted Crawleo MCP (remote streamable HTTP endpoint). Remote server at api.crawleo.dev.

not rated 11 10mo ago A tokens not measured original MIT

skill-design-guide

13623

metaskills/skill-design-guide

Skill Claude CodeCodex

Comprehensive guide for designing, building, testing, and distributing Claude skills. Use when user wants to "create a skill", "build a skill", "write a SKILL.md", "design a workflow skill", "make an MCP skill", or asks about skill structure, frontmatter, trigger phrases, or skill best practices. Walks through the…

not rated 11 9mo ago A 83 tokens

ai-shifu-course-creator

13624

ai-shifu/skills

Skill Codex

Create, edit, review, publish, manage, or analyze AI-Shifu (AI师傅) courses and their Teaching Prompts and Course Prompts in MarkdownFlow (MDF). Use for course materials, lesson design, interactions, course memory, images, deployment, platform administration, learner progress, learner profile distributions, orders…

not rated 11 changed 8d ago A 81 tokens

feature-marker

13625

Viniciuscarvalho/Feature-marker

Skill Codex

Skill-first run-through feature workflow for Claude, Codex, and Gemini. Use when the user asks to implement a feature through PRD, TechSpec, Tasks, verification, local commit, and branch handoff. The npm package installs skill files only; the LLM skill performs the workflow.

not rated 11 5mo ago A 62 tokens original MIT

legax

13626

zhanex/legax

Skill Claude CodeCodex

Use when the user wants an agent session bridged to a phone, wants remote replies polled, or wants the agent to ask a phone for approval before sensitive actions.

not rated 11 4mo ago A 37 tokens original MIT

evidence-to-skill

13627

Sanexxxx777/evidence-to-skill

Skill Codex

Convert repositories, books, incident reports, transcripts, documentation, and other source material into the smallest justified AI skill or reference artifact. Use when extracting reusable practices from external or internal sources, deciding whether material deserves promotion into agent instructions, building an…

not rated 11 2mo ago A 78 tokens original MIT

autoplan

13628

Global-mindee/WAY

Skill Codex

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…

not rated 11 2mo ago A 152 tokens original MIT

pi-subagents

13629

ethanolivertroy/my-agent-stuff

Skill Claude CodeCodex

Delegate work to builtin or custom subagents with single-agent, chain, parallel, async, forked-context, and intercom-coordinated workflows. Use for advisory review, implementation handoffs, and multi-step tasks where a single agent should stay in control while other agents contribute context, planning, or execution.

not rated 11 4mo ago A 68 tokens original MIT

sunzi-strategy-advisor

13630

yangyixxxx/sunzi-strategy-advisor

Skill Claude CodeCodex

A strategy adviser that uses the ideas of Sun Tzu, the ancient Chinese military thinker, as a structured way to examine difficult business decisions. It asks questions first, then produces a written strategy diagnosis.

not rated 11 3mo ago A 177 tokens original MIT

kevin

13631

kcass16/kevin

Skill Claude CodeCodex

Kevin is your AI legal sidekick for AI startups. Use this skill for ANY legal, compliance, or regulatory task related to AI — reviewing vendor contracts, drafting AI addendums/DPAs, classifying risk under EU AI Act or CAIA, writing AI governance policies, privacy notices, threat model assessments, enterprise due…

not rated 11 8mo ago A 159 tokens

sequential-thinking

13632

mohankrishnaalavala/context-router

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

Adds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package.

not rated 11 5mo ago A tokens not measured

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: